Masterclass
Sparse Regression
30 August – 1 September 2016 CRiSM Masterclass Sparse Regression
Organization: Joris Bierkens with thanks to Mark Fiecas Administrative support: Olivia Garcia-Hernandez
Contents
1 Practical Details 2 1.1 Conference Webpages ...... 2 1.2 Registration and Venue ...... 2 1.3 Getting Here ...... 2 1.4 Accommodation ...... 2 1.5 Internet Access ...... 3 1.6 Facilities ...... 3
2 Help, Information & Telephone Numbers 3 2.1 Department ...... 3 2.2 Emergency Numbers ...... 3 2.3 Transport ...... 3
3 Timetable 4 3.1 Tuesday 30 August ...... 4 3.2 Wednesday 31 August ...... 4 3.3 Thursday 1 September ...... 5
4 Scope 6 4.1 Richard Samworth (Cambridge): High-dimensional statistical inference ...... 6 4.2 Jianqing Fan (Princeton): Sparse Statistical Learning and Inference ...... 7
5 Posters 8
6 Participant List 10
A Warwick Conferences Delegate Information 12
B Warwick Conferences FAQ 14
C Campus Map 16
1 1 Practical Details
1.1 Conference Webpages • http://www2.warwick.ac.uk/sparse-regression
1.2 Registration and Venue • Registration: 9.30-10.30, Tuesday 30 August, Zeeman Building (map location H5-6), Atrium, which is located just behind the main entrance.
• Coffee and lunch: are provided in the Atrium of the Statistics Department.
• Lectures: Maths & Stats Building, MS.01. The lecture room MS.01 is located on the ground floor next to the Atrium.
• Poster session and reception: Tuesday 30 August, 17.00 – 18.30, Atrium. See Section 5 for an overview of posters on display.
• Masterclass dinner: 18.00, Wednesday 31 August, Radcliffe (map location F4). Estimated end time 21.00.
• Breakfast (for participants with on-campus accommodation only): 7.30-9.30 (Tue-Thu), Rootes Building. The Rootes staff has kindly agreed to keep breakfast open until 9.30 instead of the usual 9.00. However, anyone arriving after 9.00 may need to have their breakfast cooked to order to ensure it is fresh.
• Lunch: Mathematics and Statistics Building, Atrium.
• Dinner is not organized (with the exception of the masterclass dinner on Wednesday, for those who regis- tered for this). Various options for dinner are available on campus (see the campus map on the back).
• End of program: Thursday, 15.10.
1.3 Getting Here • Information on getting to the University of Warwick from Coventry, as well as from other directions locally and further afield, can be found at http://www.warwick.ac.uk/about/visiting/.
• Parking permits can be acquired at no further cost at https://carparking.warwick.ac.uk/ events/crism-master-class-on-sparse-regression.
• See Appendix A and B for further details.
1.4 Accommodation • Accommodation is in en-suite rooms on campus in either the Arthur Vick, Bluebell or Jack Martin resi- dences (on the campus map, see Appendix C). Keys can be collected from the Conference Reception in the Student Union Atrium, map location E5. All rooms have linen and toiletries. Kitchen facilities are available. Rooms will be available after 15:00 for check in. All bedrooms must be vacated by 9.30 on the day of departure.
• Check in closes at 22.45. When arriving after this hour contact Conference Reception to arrange late key collection ([email protected] or 02476 528910).
• See Appendix A, and B for further details.
2 1.5 Internet Access • Campus: Wireless access is most easily available via eduroam which is supported across most of the Warwick campus. Speak to one of the organisers for details of other options.
• Accommodation: Wireless access is available, ask for log-in details whenever you check-in to your accommodation.
1.6 Facilities - See Map • Supermarket, Food and Drink Outlets: http://www.warwickretail.com See https://www2.warwick.ac.uk/services/retail/openingtimes/ for opening times.
• Arts Centre: http://www.warwickartscentre.co.uk
• Sports Centre: http://www.warwick.ac.uk/sport/
• Health Centre: http://www.uwhc.org.uk
• Pharmacy: Student Union Atrium
2 Help, Information & Telephone Numbers
2.1 Department • Address: Department of Statistics, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL
• Fax: 024 7652 4532
• Webpage: http://www.warwick.ac.uk/stats
• Organization: Joris Bierkens, [email protected]
• Administrative support: Olivia Garcia-Hernandez, [email protected], 024 7652 2177
2.2 Emergency Numbers • Emergency: Internal - 22222; External - 024 7652 2222
• Security: Internal - 22083; External - 024 7652 2083
2.3 Transport • Swift Taxis (Coventry): 024 7676 7676
• Trinity Street Taxis: 024 7699 9999
• National Rail Enquiries: 08457 484 950
3 3 Timetable
All activities will take place in the Zeeman Building (map location H5-6), with talks in room MS.01 (signposted from lobby), unless otherwise stated.
3.1 Tuesday 30 August
Time Activity Location
9.30 – 10.30 Registration & Coffee Atrium
10.30 – 12.00 Lecture MS.01
12.00 – 13.30 Lunch break Atrium
13.30 – 15.00 Lecture MS.01
15.00 – 15.30 Coffee break Atrium
15.30 – 17.00 Lecture MS.01
17.00 – 18.30 Reception and poster session Atrium
3.2 Wednesday 31 August
Time Activity Location
10.00 – 10.30 Coffee Atrium
10.30 – 12.00 Lecture MS.01
12.00 – 13.30 Lunch break Atrium
13.30 – 15.00 Lecture MS.01
15.00 – 15.30 Coffee break Atrium
15.30 – 17.00 Lecture MS.01
18.00 – 21.00 Gala Dinner Radcliffe (map location F4)
4 3.3 Thursday 1 September
Time Activity Location
10.00 – 10.30 Coffee Atrium
10.30 – 12.00 Lecture MS.01
12.00 – 13.30 Lunch break Atrium
13.30 – 15.00 Lecture MS.01
15.00 – 15.10 Closing remarks MS.01
5 4 Scope
4.1 Richard Samworth (Cambridge): High-dimensional statistical inference Lecture 1: Classical theory Review of the linear model, geometry of orthogonal projections, hypothesis testing, examples. Ridge regression.
Lecture 2: Modern high-dimensional statistics Model selection via, e.g., information criteria. Definition of the Lasso and its geometry. Uniqueness of Lasso solutions. Prediction and estimation properties.
Lecture 3: The Lasso and beyond Selection consistency of the Lasso. Computation. Brief discussion of other penalty functions, other models, e.g. grouped variables.
Lecture 4: Multiple testing and Complementary Pairs Stability Selection Familywise error rate and Bonferroni procedure; False Discovery Rate and Benjamini–Hochberg procedure. Brief discussion of extensions. I will then use the remaining time to give an exposition of some of my own work in this area. Complementary Pairs Stability Selection is a technique for improving the performance of any existing variable selection algorithm, by aggregating the results of applying it on subsamples of the data.
6 4.2 Jianqing Fan (Princeton): Sparse Statistical Learning and Inference High-dimensionality and Big Data characterize many contemporary statistical problems from genomics and genetics to finance and economics. We first outline a unified approach to ultrahigh dimensional variable selection problems and then focus on penalized likelihood methods which are fundamentally important building blocks to ultra-high dimensional variable selection. We will also introduce variable screening methods as well as methods for guarding against suprious discoveries. Algorithms for solving penalized likelihood methods as well as Big Data computing will also be introduced. Topics to be covered include:
1. Sparse Learning via penalization
1.1 Introduction 1.2 Penalized Quasi-likelihood 1.3 Properties 1.4 One-Step Estimator 1.5 Analysis of Decomposable Regularization
2. Screening and Selection
2.1 Independence Screening 2.2 Iteratively Independent Learning 2.3 Conditional Sure Independence Screening
3. Control of Algorithmic Complexity and Statistical Error
3.1 Introduction 3.2 Overview of Gradient Methods 3.3 Iterative Local Adaptive MM 3.4 Theoretical Properties 3.5 Numerical results
4. Distributed Estimation and Inference
4.1 Introduction 4.2 Summary of Ideas and Results 4.3 Distributed statistical inference 4.4 Distributed estimation 4.5 Simulation performance
7 5 Posters
1. Non-Concave Penalized Log-Likelihood in Linear Mixed-Effect Models and the Regularized Selection of Fixed Effects Abhik Ghosh University of Oslo
2. Interpolation between Compact Binary Population Synthesis Models Jim Barrett University of Birmingham
3. Representing sparse Gaussian DAGs as sparse R-vines allowing for non-Gaussian dependence Dominik Mueller Technical University of Munich
4. Degrees of Freedom for Piecewise Lipschitz Estimators Frederik Riis Mikkelsen University of Copenhagen
5. Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation Akash Srivastava University of Edinburgh
6. Functional Inference Diego Granziol University of Oxford
7. Inference on covariance operators via concentration inequalities Adam B Kashlak University of Cambridge
8. Empirical comparison of penalised linear regression methods in high-dimensional settings Fan Wang University of Cambridge
9. Efficient Sampling in Bayesian Unlabelled Shape Analysis Anamul Haque Sajib University of Nottingham
8 10. Misleading Metrics: On Evaluating Machine Learning for Malware with Confidence Roberto Jordaney Royal Holloway University of London
11. Learning X given Y, in the absence of Training Data Cedric Spire University of Leicester
12. Distinguishing Distributions with Interpretable Features Wittawat Jitkrittum University College London
13. RSPINN: Redshift Space Power spectrum Interpolation with Neural Networks Joey Faulkner University of Edinburgh
14. Conditional density estimation of mixed continuous and categorical data Lena Reichmann University of Mannheim
15. Survival prognosis and variable selection: A case study for metastatic castration resistant prostate cancer patients Søren Wengel Mogensen University of Copenhagen
16. Testing for association between RNA-Seq and high-dimensional data Armin Rauschenberger VU Medical Center Amsterdam
17. Unbiased estimation of the volume of a convex body Nikolay Baldin University of Cambridge
18. Misleading Metrics: On Evaluating Machine Learning for Malware with Confidence Kumar Sharad Royal Holloway
9 6 Participant List
# First Name Surname Email Affiliation 1 Rodrigo Abrunhosa Collazo [email protected] University of Warwick 2 Vincent Adam [email protected] Gatsby Unit, UCL 3 Cathrine Aeckerle [email protected] Universitt Mannheim 4 Khaled Alqahtani [email protected] University of Leeds 5 Mohammed A Alshahrani [email protected] University of Leeds 6 Peter Andras [email protected] Keele University 7 Alejandra Avalos Pacheco [email protected] University of Warwick 8 Nikolay Baldin [email protected] University of Cambridge 9 Laura Barlow [email protected] Lancaster University 10 Jim Barrett [email protected] University of Birmingham 11 Joris Bierkens [email protected] University of Warwick 12 Cyril Chimisov [email protected] University of Warwick 13 Nayia Constantinou [email protected] University of Warwick 14 Jacques Dark [email protected] University of Warwick 15 Sonali Das [email protected] Council for Scientific and Industrial Research 16 Jianqing Fan [email protected] Princeton University 17 Joey Faulkner [email protected] University of Edinburgh 10 18 Phoenix Feng [email protected] London School of Economics 19 Habib Ganjgahi [email protected] University of Warwick 20 Abhik Ghosh [email protected] Postdoctoral Research Fellow 21 Diego Granziol [email protected] University of Oxford 22 Haziq Jamil [email protected] London School of Economics 23 Tom Jin [email protected] University of Warwick 24 Wittawat Jitkrittum [email protected] Gatsby Unit, UCL 25 Roberto Jordaney [email protected] Royal Holloway, University of London 26 Adam Kashlak [email protected] University of Cambridge 27 Irina Kholodenko [email protected] University of Warwick 28 Jere Koskela [email protected] University of Warwick 29 Alexander Kreiss [email protected] University of Heidelberg 30 Tony Lawrance [email protected] University of Warwick 31 Chenlei Leng [email protected] University of Warwick 32 Roberto Leyva [email protected] Computer Science 33 Itay Lieder [email protected] Hebrew University of Jerusalem 34 Samuel Livingstone [email protected] University of Bristol 35 Xavier Loizeau [email protected] Universitt Heidelberg 36 Chuoxin Ma [email protected] University of Manchester 37 Hyeyoung Maeng [email protected] London School of Economics 38 Frederik Riis Mikkelsen [email protected] University of Copenhagen 39 Sren Wengel Mogensen [email protected] University of Copenhagen Continued on next page # First Name Surname Email Affiliation 40 Dominik Mueller [email protected] Technical University of Munich 41 Bertrand Nortier [email protected] University of Bristol 42 Nick Parsons [email protected] University of Warwick 43 Iliana Peneva [email protected] University of Warwick 44 Diego Andres Perez Ruiz [email protected] Manchester University 45 Murray Pollock [email protected] University of Warwick 46 Cheng Qian [email protected] London School of Economics 47 Xinghao Qiao [email protected] London School of Economics 48 Armin Rauschenberger [email protected] VU Medical Center Amsterdam 49 Lena Reichmann [email protected] Universitt Mannheim 50 Gareth Roberts [email protected] University of Warwick 51 Giovanni Romeo [email protected] University of Oslo 52 Ragvir Sabharwal [email protected] London School of Economics 53 Anamul Sajib [email protected] University of Nottingham 54 Pantelis Samartsidis [email protected] University of Warwick 55 Richard Samworth [email protected] University of Cambridge 56 Claudia Schillings [email protected] University of Warwick 57 David Selby [email protected] University of Warwick 58 Kumar Sharad [email protected] Royal Holloway, University of London 59 Jim Skinner [email protected] University of Warwick 11 60 Cedric Spire [email protected] University of Leicester 61 Steven Squires [email protected] University of Southampton 62 Akash Srivastava [email protected] University of Edinburgh 63 Aretha Teckentrup [email protected] University of Warwick 64 Samuel Tickle [email protected] University of Lancaster 65 Sara Wade [email protected] University of Warwick 66 Fan Wang [email protected] MRC Biostatistics Unit 67 Kangrui Wang [email protected] University of Leicester 68 Weining Wang [email protected] City U London and Humboldt U at Berlin 69 Yanxin Wang [email protected] 70 Liang Yan [email protected] University of Warwick 71 Mingda Yuan [email protected] 72 Chi Zhang [email protected] 73 Qiang Zhang [email protected] University of Warwick 74 Yu Zheng [email protected] Imperial College London Anything is possible
Delegate Joining Instructions Warwick Conferences Conference Park
We are delighted that you will be joining us at the University of Warwick. Please bring these instructions with you as you will find them useful whilst you are on campus.
Getting to campus and car parking: